Model Card on HF 🤗: https://huggingface.co/apple/FastVLM-1.5B
FastVLM 1.5B Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
FastVLM 1.5B Parameters and Internals
| LLM Name | FastVLM 1.5B |
| Repository 🤗 | https://huggingface.co/apple/FastVLM-1.5B |
| Model Size | 13b |
| Required VRAM | 3.8 GB |
| Updated | 2025-08-31 |
| Maintainer | apple |
| Model Type | llava_qwen2 |
| Model Files | |
| Model Architecture | LlavaQwen2ForCausalLM |
| License | apple-amlr |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.39.3 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to FastVLM 1.5B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| FastVLM 0.5B | 32K / 1.5 GB | 701 | 70 |
Note: green Score (e.g. "73.2") means that the model is better than apple/FastVLM-1.5B .
Rank the FastVLM 1.5B Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 51022 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124